參考 pytorch: 準備、訓練和測試自己的圖片數(shù)據(jù)

1及汉、下載數(shù)據(jù)

下載原始地址fashion-mnist
轉(zhuǎn)換圖片代碼如下（應該是版本問題，對原代碼label讀取作了輕微調(diào)整）：

import os
from skimage import io
import torchvision.datasets.mnist as mnist

root="D:/data/fashion_mnist/"#數(shù)據(jù)集合地址 數(shù)據(jù)要先解壓縮
train_set = (
    mnist.read_image_file(os.path.join(root, 'train-images-idx3-ubyte')),
    mnist.read_label_file(os.path.join(root, 'train-labels-idx1-ubyte'))
        )
test_set = (
    mnist.read_image_file(os.path.join(root, 't10k-images-idx3-ubyte')),
    mnist.read_label_file(os.path.join(root, 't10k-labels-idx1-ubyte'))
        )
print("training set :",train_set[0].size())
print("test set :",test_set[0].size())

def convert_to_img(train=True):
    if(train):
        f=open(root+'train.txt','w')
        data_path=root+'/train/'
        if(not os.path.exists(data_path)):
            os.makedirs(data_path)
        for i, (img,label) in enumerate(zip(train_set[0],train_set[1])):
            img_path=data_path+str(i)+'.jpg'
            io.imsave(img_path,img.numpy())
            f.write(img_path+' '+str(label.item())+'\n')
        f.close()
    else:
        f = open(root + 'test.txt', 'w')
        data_path = root + '/test/'
        if (not os.path.exists(data_path)):
            os.makedirs(data_path)
        for i, (img,label) in enumerate(zip(test_set[0],test_set[1])):
            img_path = data_path+ str(i) + '.jpg'
            io.imsave(img_path, img.numpy())
            f.write(img_path + ' ' + str(label.item()) + '\n')
        f.close()

convert_to_img(True)
convert_to_img(False)

2、數(shù)據(jù)讀取及分類任務

其中數(shù)據(jù)讀取部分采用了參考網(wǎng)站的代碼桑腮，網(wǎng)絡訓練部分則用了mnist簡易分類網(wǎng)絡

import torch
from torch.autograd import Variable
from torchvision import transforms
from torch.utils.data import Dataset, DataLoader
from PIL import Image
import torch.nn.functional as F
root="D:/data/fashion_mnist/"

#----數(shù)據(jù)處理階段
def default_loader(path):
    return Image.open(path).convert('RGB')
class MyDataset(Dataset):
    def __init__(self, txt, transform=None, target_transform=None, loader=default_loader):
        fh = open(txt, 'r')
        imgs = []
        for line in fh:
            line = line.strip('\n')
            line = line.rstrip()
            words = line.split()
            imgs.append((words[0],int(words[1])))
        self.imgs = imgs
        self.transform = transform
        self.target_transform = target_transform
        self.loader = loader

    def __getitem__(self, index):
        fn, label = self.imgs[index]
        img = self.loader(fn)
        if self.transform is not None:
            img = self.transform(img)
        return img,label

    def __len__(self):
        return len(self.imgs)

train_data=MyDataset(txt=root+'train.txt', transform=transforms.ToTensor())
test_data=MyDataset(txt=root+'test.txt', transform=transforms.ToTensor())
train_loader = DataLoader(dataset=train_data, batch_size=64, shuffle=True)
test_loader = DataLoader(dataset=test_data, batch_size=64)

#----構(gòu)建網(wǎng)絡及訓練部分
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Sequential(
            torch.nn.Conv2d(3, 32, 3, 1, 1),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(2))
        self.conv2 = torch.nn.Sequential(
            torch.nn.Conv2d(32, 64, 3, 1, 1),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(2)
        )
        self.conv3 = torch.nn.Sequential(
            torch.nn.Conv2d(64, 64, 3, 1, 1),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(2)
        )
        self.dense = torch.nn.Sequential(
            torch.nn.Linear(64 * 3 * 3, 128),
            torch.nn.ReLU(),
            torch.nn.Linear(128, 10)
        )

    def forward(self, x):
        conv1_out = self.conv1(x)
        conv2_out = self.conv2(conv1_out)
        conv3_out = self.conv3(conv2_out)
        res = conv3_out.view(conv3_out.size(0), -1)
        out = self.dense(res)
        return out

DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = Net().to(DEVICE)
print(model)
EPOCHS=15

optimizer = torch.optim.Adam(model.parameters())
loss_func = torch.nn.CrossEntropyLoss()
def train(model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.cross_entropy(output, target)
        loss.backward()
        optimizer.step()
        if(batch_idx+1)%200 == 0: 
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))

def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item() 
            pred = output.max(1, keepdim=True)[1] 
            correct += pred.eq(target.view_as(pred)).sum().item()
    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))

for epoch in range(1, EPOCHS + 1):
    train(model, DEVICE, train_loader, optimizer, epoch)
    test(model, DEVICE, test_loader)

3痘绎、實驗結(jié)果

訓練了15個epoch津函，測試準確率為91.46%

訓練結(jié)果